# AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay

arXiv: https://arxiv.org/abs/2502.16789 · HTML: https://mlsanity.com/paper/2502.16789/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qlib: An AI-oriented Quantitative Investment Platform](https://mlsanity.com/paper/2009.11189/) (2020)
- [Language Models Can Teach Themselves to Program Better](https://mlsanity.com/paper/2207.14502/) (2022)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance](https://mlsanity.com/paper/2111.09395/) (2021)
- [On the Creativity of Large Language Models](https://mlsanity.com/paper/2304.00008/) (2023)
- [Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning](https://mlsanity.com/paper/2306.12964/) (2023)
- [LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction](https://mlsanity.com/paper/2406.10811/) (2024)
- [AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment](https://mlsanity.com/paper/2103.16196/) (2021)
- [Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport](https://mlsanity.com/paper/2106.12950/) (2021)
- [AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors](https://mlsanity.com/paper/2406.18394/) (2024)
- [Can Large Language Models Unlock Novel Scientific Research Ideas?](https://mlsanity.com/paper/2409.06185/) (2024)
- [Collaborative Evolving Strategy for Automatic Data-Centric Development](https://mlsanity.com/paper/2407.18690/) (2024)
- [Towards Data-Centric Automatic R&D](https://mlsanity.com/paper/2404.11276/) (2024)

## Built on by (most cited first, 30 of 42)

- [Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining](https://mlsanity.com/paper/2505.11122/) (2025)
- [QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining](https://mlsanity.com/paper/2602.07085/) (2026)
- [Cognitive Alpha Mining via LLM-Driven Code-Based Evolution](https://mlsanity.com/paper/2511.18850/) (2025)
- [Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents](https://mlsanity.com/paper/2601.10955/) (2026)
- [Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents](https://mlsanity.com/paper/2603.00902/) (2026)
- [LiveTradeBench: Seeking Real-World Alpha with Large Language Models](https://mlsanity.com/paper/2511.03628/) (2025)
- [AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining](https://mlsanity.com/paper/2508.13174/) (2025)
- [Evaluating LLMs in Finance Requires Explicit Bias Consideration](https://mlsanity.com/paper/2602.14233/) (2026)
- [MASS: Muli-agent simulation scaling for portfolio construction](https://mlsanity.com/paper/2505.10278/) (2025)
- [Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2512.23515/) (2025)
- [From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery](https://mlsanity.com/paper/2605.15412/) (2026)
- [Hubble: An LLM-Driven Agentic Framework for Safe, Diverse, and Reproducible Alpha Factor Discovery](https://mlsanity.com/paper/2604.09601/) (2026)
- [SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents](https://mlsanity.com/paper/2605.06822/) (2026)
- [AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution](https://mlsanity.com/paper/2602.11917/) (2026)
- [FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment](https://mlsanity.com/paper/2603.16365/) (2026)
- [AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents](https://mlsanity.com/paper/2606.20625/) (2026)
- [AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining](https://mlsanity.com/paper/2607.26642/) (2026)
- [AQuA: Recursively Self-Improving Quantitative Trading Research Agents](https://mlsanity.com/paper/2608.12841/) (2026)
- [FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data](https://mlsanity.com/paper/2510.25223/) (2025)
- [MEME: Modeling the Evolutionary Modes of Financial Markets](https://mlsanity.com/paper/2602.11918/) (2026)
- [X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution](https://mlsanity.com/paper/2607.08332/) (2026)
- [AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative Investment](https://mlsanity.com/paper/2608.28632/) (2026)
- [From Natural Language to Executable Option Strategies via Large Language Models](https://mlsanity.com/paper/2603.16434/) (2026)
- [AlphaCrafter: Harnessing Multi-Agent Workflows for Cross-Sectional Quantitative Trading](https://mlsanity.com/paper/2605.05580/) (2026)
- [Market-Dependent Communication in Multi-Agent Alpha Generation](https://mlsanity.com/paper/2511.13614/) (2025)
- [Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey](https://mlsanity.com/paper/2601.19927/) (2026)
- [Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems](https://mlsanity.com/paper/2606.08285/) (2026)
- [EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading](https://mlsanity.com/paper/2607.12455/) (2026)
- [FinHardBench: Can LLMs Generate Latency-Aware Hardware for Financial Computing?](https://mlsanity.com/paper/2608.00909/) (2026)
- [AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery](https://mlsanity.com/paper/2608.01303/) (2026)

## Abstract (arXiv)

Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However, the pervasive issue of alpha decay, where factors lose their predictive power over time, poses a significant challenge for alpha mining. Traditional methods like genetic programming face rapid alpha decay from overfitting and complexity, while approaches driven by Large Language Models (LLMs), despite their promise, often rely too heavily on existing knowledge, creating homogeneous factors that worsen crowding and accelerate decay. To address this challenge, we propose AlphaAgent, an autonomous framework that effectively integrates LLM agents with ad hoc regularizations for mining decay-resistant alpha factors. AlphaAgent employs three key mechanisms: (i) originality enforcement through a similarity measure based on abstract syntax trees (ASTs) against existing alphas, (ii) hypothesis-factor alignment via LLM-evaluated semantic consistency between market hypotheses and generated factors, and (iii) complexity control via AST-based structural constraints, preventing over-engineered constructions that are prone to overfitting. These mechanisms collectively guide the alpha generation process to balance originality, financial rationale, and adaptability to evolving market conditions, mitigating the risk of alpha decay. Extensive evaluations show that AlphaAgent outperforms traditional and LLM-based methods in mitigating alpha decay across bull and bear markets, consistently delivering significant alpha in Chinese CSI 500 and US S&P 500 markets over the past four years. Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors.